input_data.py直接先将图片路径和标签对应为两个列表,然后用Tensorflow的模块生产批次batch
import os import tensorflow as tf import matplotlib.pyplot as plt import numpy as np train_path = 'D:/python学习/神经网络动物分类/train/' test_path = 'D:/python学习/神经网络动物分类/test/' classes = ["airplane", "automobile","bird","cat","deer", "dog","frog","horse","ship","truck"] def get_files(file_dir): # file_dir: 文件夹路径 # return: 乱序后的图片和标签 img_list = [] label_list = [] for index, name in enumerate(classes): class_path = file_dir + name + "/" for img_name in os.listdir(class_path): img_path = class_path + img_name img_list.append(img_path) label_list.append(int(index)) temp = np.array([img_list, label_list]) temp = temp.transpose() # 转置 np.random.shuffle(temp) img_list = list(temp[:, 0]) label_list = list(temp[:, 1]) label_list = [int(i) for i in label_list] return img_list, label_list def get_batch(image, label, image_W, image_H, batch_size, capacity): # image, label: 要生成batch的图像的地址和标签list # image_W, image_H: 图片的宽高 # batch_size: 每个batch有多少张图片 # capacity: 队列容量 # return: 图像和标签的batch # 将python.list类型转换成tf能够识别的格式 image = tf.cast(image, tf.string) label = tf.cast(label, tf.int32) # 生成队列 input_queue = tf.train.slice_input_producer([image, label]) image_contents = tf.read_file(input_queue[0]) label = input_queue[1] image = tf.image.decode_jpeg(image_contents, channels=3) image = tf.image.resize_images(image, [image_H, image_W], method=tf.image.ResizeMethod.NEAREST_NEIGHBOR) image = tf.cast(image, tf.float32) image_batch, label_batch = tf.train.batch([image, label], batch_size=batch_size, num_threads=64, # 线程 capacity=capacity) return image_batch, label_batch # 测试两个函数是否成功运行 """ if __name__ == '__main__': BATCH_SIZE = 2 CAPACITY = 256 IMG_W = 32 IMG_H = 32 image_list, label_list = get_files(train_path) image_batch, label_batch = get_batch(image_list, label_list, IMG_W, IMG_H, BATCH_SIZE, CAPACITY) with tf.Session() as sess: i = 0 coord = tf.train.Coordinator() threads = tf.train.start_queue_runners(coord=coord) try: while not coord.should_stop() and i < 1: img, label = sess.run([image_batch, label_batch]) for j in np.arange(BATCH_SIZE): print("label: %d" % label[j]) plt.imshow(img[j, :, :, :]) plt.show() i += 1 except tf.errors.OutOfRangeError: print("done!") finally: coord.request_stop() coord.join(threads) """
model.py函数实现了模型以及预测
#coding=utf-8 import tensorflow as tf def inference(images, batch_size, n_classes): with tf.variable_scope('conv1') as scope: # 卷积盒的为 3*3 的卷积盒,图片厚度是3,输出是16个featuremap weights = tf.get_variable('weights', shape=[3, 3, 3, 16], dtype=tf.float32, initializer=tf.truncated_normal_initializer(stddev=0.1, dtype=tf.float32)) biases = tf.get_variable('biases', shape=[16], dtype=tf.float32, initializer=tf.constant_initializer(0.1)) conv = tf.nn.conv2d(images, weights, strides=[1, 1, 1, 1], padding='SAME') pre_activation = tf.nn.bias_add(conv, biases) conv1 = tf.nn.relu(pre_activation, name=scope.name) with tf.variable_scope('pooling1_lrn') as scope: pool1 = tf.nn.max_pool(conv1, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1], padding='SAME', name='pooling1') norm1 = tf.nn.lrn(pool1, depth_radius=4, bias=1.0, alpha=0.001 / 9.0, beta=0.75, name='norm1') with tf.variable_scope('conv2') as scope: weights = tf.get_variable('weights', shape=[3, 3, 16, 16], dtype=tf.float32, initializer=tf.truncated_normal_initializer(stddev=0.1, dtype=tf.float32)) biases = tf.get_variable('biases', shape=[16], dtype=tf.float32, initializer=tf.constant_initializer(0.1)) conv = tf.nn.conv2d(norm1, weights, strides=[1, 1, 1, 1], padding='SAME') pre_activation = tf.nn.bias_add(conv, biases) conv2 = tf.nn.relu(pre_activation, name='conv2') # pool2 and norm2 with tf.variable_scope('pooling2_lrn') as scope: norm2 = tf.nn.lrn(conv2, depth_radius=4, bias=1.0, alpha=0.001 / 9.0, beta=0.75, name='norm2') pool2 = tf.nn.max_pool(norm2, ksize=[1, 3, 3, 1], strides=[1, 1, 1, 1], padding='SAME', name='pooling2') with tf.variable_scope('local3') as scope: reshape = tf.reshape(pool2, shape=[batch_size, -1]) dim = reshape.get_shape()[1].value weights = tf.get_variable('weights', shape=[dim, 128], dtype=tf.float32, initializer=tf.truncated_normal_initializer(stddev=0.005, dtype=tf.float32)) biases = tf.get_variable('biases', shape=[128], dtype=tf.float32, initializer=tf.constant_initializer(0.1)) local3 = tf.nn.relu(tf.matmul(reshape, weights) + biases, name=scope.name) # local4 with tf.variable_scope('local4') as scope: weights = tf.get_variable('weights', shape=[128, 128], dtype=tf.float32, initializer=tf.truncated_normal_initializer(stddev=0.005, dtype=tf.float32)) biases = tf.get_variable('biases', shape=[128], dtype=tf.float32, initializer=tf.constant_initializer(0.1)) local4 = tf.nn.relu(tf.matmul(local3, weights) + biases, name='local4') # softmax with tf.variable_scope('softmax_linear') as scope: weights = tf.get_variable('softmax_linear', shape=[128, n_classes], dtype=tf.float32, initializer=tf.truncated_normal_initializer(stddev=0.005, dtype=tf.float32)) biases = tf.get_variable('biases', shape=[n_classes], dtype=tf.float32, initializer=tf.constant_initializer(0.1)) softmax_linear = tf.add(tf.matmul(local4, weights), biases, name='softmax_linear') return softmax_linear def losses(logits, labels): with tf.variable_scope('loss') as scope: cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits \ (logits=logits, labels=labels, name='xentropy_per_example') loss = tf.reduce_mean(cross_entropy, name='loss') tf.summary.scalar(scope.name + '/loss', loss) return loss def trainning(loss, learning_rate): with tf.name_scope('optimizer'): optimizer = tf.train.AdamOptimizer(learning_rate= learning_rate) global_step = tf.Variable(0, name='global_step', trainable=False) train_op = optimizer.minimize(loss, global_step= global_step) return train_op def evaluation(logits, labels): with tf.variable_scope('accuracy') as scope: correct = tf.nn.in_top_k(logits, labels, 1) correct = tf.cast(correct, tf.float16) accuracy = tf.reduce_mean(correct) tf.summary.scalar(scope.name + '/accuracy', accuracy) return accuracy
train.py函数实现了训练过程
import os import numpy as np import tensorflow as tf import input_data import model N_CLASSES = 10 IMG_H = 32 IMG_W = 32 BATCH_SIZE = 200 CAPACITY = 2000 MAX_STEP = 15000 learning_rate = 0.0001 def run_training(): train_dir = "D:\\python学习\\神经网络动物分类\\train\\" logs_train_dir = "logs\\" train, train_label = input_data.get_files(train_dir) train_batch, train_label_batch = input_data.get_batch(train, train_label, IMG_W, IMG_H, BATCH_SIZE, CAPACITY) train_logits = model.inference(train_batch, BATCH_SIZE, N_CLASSES) train_loss = model.losses(train_logits, train_label_batch) train_op = model.trainning(train_loss, learning_rate) train_acc = model.evaluation(train_logits, train_label_batch) summary_op = tf.summary.merge_all() sess = tf.Session() train_writer = tf.summary.FileWriter(logs_train_dir, sess.graph) saver = tf.train.Saver() sess.run(tf.global_variables_initializer()) coord = tf.train.Coordinator() threads = tf.train.start_queue_runners(sess=sess, coord=coord) try: for step in np.arange(MAX_STEP): if coord.should_stop(): break _, tra_loss, tra_acc = sess.run([train_op, train_loss, train_acc]) if step % 100 == 0: print("Step %d, train loss = %.2f, train accuracy = %.2f%%" % (step, tra_loss, tra_acc)) summary_str = sess.run(summary_op) train_writer.add_summary(summary_str, step) if step % 2000 == 0 or (step + 1) == MAX_STEP: checkpoint_path = os.path.join(logs_train_dir, "model.ckpt") saver.save(sess, checkpoint_path, global_step=step) except tf.errors.OutOfRangeError: print("Done training -- epoch limit reached.") finally: coord.request_stop() coord.join(threads) sess.close() if __name__ == '__main__': run_training()